Created
April 7, 2017 13:55
-
-
Save btskinner/a1f5bc5c1c32b48d4f45b05d2531e423 to your computer and use it in GitHub Desktop.
Reshaping data in R
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
library(dplyr) | |
library(tidyr) | |
## make wide toy data | |
df <- data.frame(schid = c('A','B','C','D'), | |
year = 2013, | |
var_x = 1:4, | |
var_y = 5:8, | |
var_z = 9:12, | |
stringsAsFactors = FALSE) %>% | |
tbl_df() | |
## gather (wide --> long) | |
df_long <- df %>% | |
gather(var, value, -c(schid, year)) %>% | |
mutate(var = gsub('var_', '', var)) %>% | |
arrange(schid, var) | |
## spread (long --> wide) | |
df_wide <- df_long %>% | |
mutate(var = gsub('(.*)', 'var_\\1', var)) %>% | |
spread(var, value) %>% | |
arrange(schid) | |
## print df | |
df | |
df_long | |
df_wide | |
## confirm that df_wide == df | |
identical(df, df_wide) | |
## -- NOTES -- | |
## mutate() commands not strictly necessary; just for -/+ stub names | |
## tbl_df() not necessary; just makes printing nicer |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment